Install
pip install llama-index==0.14.26RAG-first agent framework — data connectors, vector indexing, query engines, and workflow-based agents.
The data framework for LLM apps. LlamaIndex turns unstructured data into agent-queryable knowledge — document loaders, vector indices, query engines, tools, and event-driven workflows with prebuilt agents.
Install
pip install llama-index==0.14.26Version
llama-index 0.14.26 (core and bundle share a version) · llama-index-workflows 2.26.1 · Python 3.10+ · checked 2026-11-19
Best for
RAG systems, document Q&A, enterprise knowledge agents.
Numbers are the comprehensive guide’s section numbers; unnumbered steps are separate pages.
Patch releases since the guide was last revised (from the upstream changelog):
compact and refine response modes; native async for StructuredLLMRerank; removed the deprecated IPEX integrations; security dependency updates.AgentWorkflow now honours an agent’s output_cls / structured_output_fn; Memory accepts any AsyncDBChatStore; async LLMRerank; many ingestion and retrieval fixes.initial_state is deep-copied per run.No breaking API changes in this range. The last breaking releases were 0.13.0 (legacy agents and QueryPipeline removed) and 0.14.0 (moved to llama-index-workflows 2.x).
import asynciofrom llama_index.core import VectorStoreIndex, SimpleDirectoryReaderfrom llama_index.core.agent.workflow import FunctionAgentfrom llama_index.core.tools import QueryEngineToolfrom llama_index.llms.openai import OpenAI
documents = SimpleDirectoryReader("data").load_data()index = VectorStoreIndex.from_documents(documents)
tool = QueryEngineTool.from_defaults( query_engine=index.as_query_engine(), name="knowledge_base", description="Answer questions about the documents",)
agent = FunctionAgent(tools=[tool], llm=OpenAI(model="gpt-6-luna"))
async def main(): response = await agent.run(user_msg="What are the key findings?") print(response)
asyncio.run(main())Ready? Start Zero → Hero Step 1 →
| Date | Version | Changes |
|---|---|---|
| 2026-10-24 | 0.14.25 / workflows 2.26.1 | Audit against an installed release. New: response modes, chat engine modes, filters, chunking and metadata extraction, sentence-window and auto-merging retrieval, HyDE, citations (comprehensive guide); span and event reference, token budgets and local tracing (observability); chat-engine route, client and tests (streaming server); cited-answer and text-to-SQL recipes. Corrected: the observability page said agents emit AgentToolCallEvent (they do not) and that token counts are only tokenizer estimates (LLM counts use the provider’s usage when reported); the ReAct and router diagrams. |
| 2026-10-24 | 0.14.25 / workflows 2.26.1 | Added the Workflows page; the Zero → Hero step for custom workflows now points to it. |
| 2026-10-21 | 0.14.25 | Zero → Hero cards now carry the comprehensive guide’s section numbers; links added for the new property graph, multimodal, LlamaParse, serving and evaluation-dataset sections; production guide rewritten. |
| 2026-10-21 | 0.14.25 | Version now read from the site’s version registry. Minimal example rewritten for FunctionAgent (the previous one used the removed ReActAgent.from_tools / .chat() API). llama-agents references replaced with AgentWorkflow and LlamaAgents/llamactl. Comprehensive guide, advanced pages and recipes re-verified against an installed copy. |
| 2026-05-19 | 0.14.22 | Version bump. |
| 2026-04-21 | 0.14.20 | Index redesigned with Zero → Hero + Jump-to-topic grid. |
| November 2025 | 0.14.8 | Initial documented version. |
Note: TypeScript implementation lives at LlamaIndex (TypeScript) — that project has since been deprecated upstream.